Transfer Learning for Avian Bioacoustics under Sparse Positive Labels
2026-08-04 • Sound
Sound
AI summaryⓘ
The authors studied how to improve automatic monitoring of bird sounds to help track biodiversity, even when labeled examples are few and incomplete. They used bird sound datasets from different sources and created a method that treats each data source as having different trustworthiness. Their approach worked better than simply combining all data and showed that choosing data carefully is important. They also found that the problem behaves like "weak supervision," where some labels are uncertain, making learning harder.
Passive acoustic monitoringTransfer learningWeak supervisionBioacousticsSparse labelsBirdCLEF datasetMulti-source learningNegative transferBiodiversity assessmentMacro average precision
Authors
Dhyey Patel, Yunting Yin
Abstract
Passive acoustic monitoring is an important tool for biodiversity assessment and wildlife conservation because it supports continuous and non-invasive monitoring of species across large spatial and temporal scales. Robust monitoring remains challenging because many datasets contain sparse positive labels, where species presences may be confirmed while unannotated species cannot be assumed absent. In this work, we study transfer learning under sparse positive labels using BirdCLEF+ 2026 as a target benchmark and BirdCLEF 2021, iNatSounds, WABAD, and BirdSet as external bioacoustic sources. We introduce a multi-source reliability framework that models heterogeneous bioacoustic datasets as distinct supervision sources with differing reliability. Our approach achieves 0.584 macro average precision and 0.860 macro AUC on public BirdCLEF+ 2026 validation labels while outperforming naive source pooling strategies. The strongest gains arise from passive acoustic monitoring datasets and biologically informed source selection. Our findings suggest that transfer learning in bioacoustics is fundamentally a weak supervision and negative transfer problem.